Presentation 2004/3/9
Examination of Partial Solution in Symbiotic Evolution for Decision Tree Generation
Noriko OTANI, Masamichi SHIMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In representing classification rules by decision trees, simplicity of tree structure is as important as predictive accuracy especially in consideration of the memory capacity and the time required to classify. This paper addresses the issue of the generation of accurate and simple decision trees based on symbiotic evolution. It is distinctive of symbiotic evolution that individuals represent partial solutions. We construct a new system SESAT2, and examine the effect of some matters for partial solutions in it. Experiments were performed with four types of SESAT2 on several datasets in UCI repository. Our results show that the differences between the four systems produce no effect in training fitness and predictive accuracy, but some effect in simplicity and training time.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) decision tree / genetic algorithm / symbiotic evolution / partial solution
Paper # AI2003-98
Date of Issue

Conference Information
Committee AI
Conference Date 2004/3/9(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Artificial Intelligence and Knowledge-Based Processing (AI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Examination of Partial Solution in Symbiotic Evolution for Decision Tree Generation
Sub Title (in English)
Keyword(1) decision tree
Keyword(2) genetic algorithm
Keyword(3) symbiotic evolution
Keyword(4) partial solution
1st Author's Name Noriko OTANI
1st Author's Affiliation Faculty of Environmental and Information Studies, Musashi Institute of Technology()
2nd Author's Name Masamichi SHIMURA
2nd Author's Affiliation Faculty of Environmental and Information Studies, Musashi Institute of Technology
Date 2004/3/9
Paper # AI2003-98
Volume (vol) vol.103
Number (no) 725
Page pp.pp.-
#Pages 6
Date of Issue